chore: migrate from Docker Compose to embedded ChromaDB and add HuggingFace Dockerfile

Author: suprit-4618

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy source code
+COPY . .
+
+# Generate Embeddings and build the embedded ChromaDB index during the Docker build
+RUN python embed.py
+RUN python insert_vectors.py
+
+# Expose Hugging Face Space default port
+EXPOSE 7860
+
+# Run FastAPI server
+CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "7860"]

docker-compose.yml

@@ -30,8 +30,9 @@ def insert_vectors():
     print(f"Connecting to ChromaDB at {BASE_URL}:{PORT}...")
 
     try:
-        # 1. Initialize ChromaDB Client
-        client = chromadb.HttpClient(host=BASE_URL, port=PORT)
+        # 1. Connect to Embedded ChromaDB
+        print("Connecting to local ChromaDB...")
+        client = chromadb.PersistentClient(path="./chroma_db")
 
         # 2. Ensure index exists
         dimension = embeddings.shape[1]

insert_vectors.py

@@ -14,7 +14,9 @@
 def search_chroma(query):
     try:
         # 1. Initialize ChromaDB Client
-        client = chromadb.HttpClient(host=BASE_URL, port=PORT)
+        # Connect to Embedded ChromaDB
+        print("Connecting to local ChromaDB...")
+        client = chromadb.PersistentClient(path="./chroma_db")
 
         # 2. Get the collection
         collection = client.get_collection(name=COLLECTION_NAME)

search.py

@@ -41,7 +41,8 @@ def search(payload: SearchQuery):
         # Encode Query
         query_vector = model.encode([payload.query])[0].tolist()
 
-        client = chromadb.HttpClient(host=BASE_URL, port=PORT)
+        # Initialize Persistent ChromaDB Client
+        client = chromadb.PersistentClient(path="./chroma_db")
         collection = client.get_collection(name=COLLECTION_NAME)
 
         results_db = collection.query(